Last active
October 26, 2015 11:16
-
-
Save lukaswelte/93bf3c019e8ca7744585 to your computer and use it in GitHub Desktop.
MapReduce Wordcount
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> { | |
private final static IntWritable one = new IntWritable(1); | |
private Text word = new Text(); | |
public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException { | |
String line = value.toString(); | |
StringTokenizer tokenizer = new StringTokenizer(line); | |
while (tokenizer.hasMoreTokens()) { | |
word.set(tokenizer.nextToken()); | |
output.collect(word, one); | |
} | |
} | |
} |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> { | |
public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException { | |
int sum = 0; | |
while (values.hasNext()) { | |
sum += values.next().get(); | |
} | |
output.collect(key, new IntWritable(sum)); | |
} | |
} |
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
package org.myorg; | |
import java.io.IOException; | |
import java.util.*; | |
import org.apache.hadoop.fs.Path; | |
import org.apache.hadoop.conf.*; | |
import org.apache.hadoop.io.*; | |
import org.apache.hadoop.mapred.*; | |
import org.apache.hadoop.util.*; | |
public class WordCount { | |
public static class Map extends MapReduceBase implements Mapper<LongWritable, Text, Text, IntWritable> { | |
private final static IntWritable one = new IntWritable(1); | |
private Text word = new Text(); | |
public void map(LongWritable key, Text value, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException { | |
String line = value.toString(); | |
StringTokenizer tokenizer = new StringTokenizer(line); | |
while (tokenizer.hasMoreTokens()) { | |
word.set(tokenizer.nextToken()); | |
output.collect(word, one); | |
} | |
} | |
} | |
public static class Reduce extends MapReduceBase implements Reducer<Text, IntWritable, Text, IntWritable> { | |
public void reduce(Text key, Iterator<IntWritable> values, OutputCollector<Text, IntWritable> output, Reporter reporter) throws IOException { | |
int sum = 0; | |
while (values.hasNext()) { | |
sum += values.next().get(); | |
} | |
output.collect(key, new IntWritable(sum)); | |
} | |
} | |
public static void main(String[] args) throws Exception { | |
JobConf conf = new JobConf(WordCount.class); | |
conf.setJobName("wordcount"); | |
conf.setOutputKeyClass(Text.class); | |
conf.setOutputValueClass(IntWritable.class); | |
conf.setMapperClass(Map.class); | |
conf.setCombinerClass(Reduce.class); | |
conf.setReducerClass(Reduce.class); | |
conf.setInputFormat(TextInputFormat.class); | |
conf.setOutputFormat(TextOutputFormat.class); | |
FileInputFormat.setInputPaths(conf, new Path(args[0])); | |
FileOutputFormat.setOutputPath(conf, new Path(args[1])); | |
JobClient.runJob(conf); | |
} | |
} |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment